TinyML: The NextGen AI Technology for Standalone Devices

DOI

10.2991/978-94-6239-707-1_15How to use a DOI?

Keywords

TinyML; Edge AI; Microcontroller (MCU); Embedded System; Resource-constrained devices; Model Compression; Model Quantization

Abstract

Currently, the world is going through an AI and ML revolution, and we have seen tremendous growth in the implementation of AI in various sectors over the last decade. Conventional AI-based systems were implemented in a cloud-centric environment, using servers with high processing power, ample storage, and high-speed internet, which consume significant power. Tiny Machine Learning (TinyML) enables conventional ML models to run directly on resource-constrained embedded devices (i.e., Microcontrollers) with limited storage, processing capabilities, and power consumption. TinyML opens a new era to shift resource-hungry and cloud-centric conventional ML models to run in tiny and standalone resource-constrained devices. TinyML is a perfect solution for deploying AI and ML applications on sensors, wearables, IoT devices, and other small devices that are used in everyday life. In this paper, we have presented an intuitive review of the possibilities of TinyML. We have presented the back-ground of TinyML, elaborated on TinyML-aware hardware platforms, tool sets for learning-to-deploy, the implementation methodology, and various use cases of TinyML. Finally, we have identified and discussed key challenges associated with this.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Satishkumar Kataria
AU  - Pankaj Prajapati
AU  - Sachin Gajar
AU  - Amit Rathod
PY  - 2026
DA  - 2026/06/18
TI  - TinyML: The NextGen AI Technology for Standalone Devices
BT  - Proceedings of the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026)
PB  - Atlantis Press
SP  - 167
EP  - 180
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-707-1_15
DO  - 10.2991/978-94-6239-707-1_15
ID  - Kataria2026
ER  -